-
It appears when using NBEATs model while Generic_architecture is set to False that there is a tensor assigned to CPU while the rest is GPU:
RuntimeError Traceback (most r…
-
**Describe the bug**
When calling "historical_forecast" or "predict" on a fittel TCN model trained using GPUs.
Happens right after calling the method.
**To Reproduce**
Steps to reproduce the …
-
- PyTorch-Forecasting version: 0.8.5
- PyTorch version: 1.8.1
- Python version: 3.7
- Operating System: windows10
TimeSeriesDataSet(
data[lambda x: x['week']
-
Hi,
thanks for the great library.
I have an usability question.
I have trained an NBeats model on a dataframe containing 16 time series as in the example (https://pytorch-forecasting.readthedoc…
-
https://github.com/cchallu/nbeatsx
I think we should implement nbeatsx in pytorch-forecasting.Nbeats is not able to use exogenous variables while nbeatsx can.
-
- PyTorch-Forecasting version: 0.8.4
- PyTorch Lightning version: 1.1.8
- Python version: 1.8.1
- Operating System: Ubuntu 18.4
### Expected behavior
Trying to **log the computation graph to …
-
- PyTorch-Forecasting version:
- PyTorch version:
- Python version:
- Operating System:
Hi, Thanks for this library!!!
I want to predict the market price(Open price) of a stock.
I'm trying to …
-
I am getting error when running this example when running NBeats.ipynb while running the following command. If I remove stack_types or set it as ('trend','seasonality') it works fine. But it gives err…
-
**Describe the bug**
It complains tensors are on GPU and CPU. nbeats.py works better if you add .cuda() to each torch.zero
**To Reproduce**
Run NBEATS-examples notebook.
**Expected behavior**…
-
Hi @jdb78 ,
I am trying to customize your N-Beats implementation to use `SELU()` instead of `ReLU()` activation function.
It's easy to replace it and use PyTorch's implementation, but SELU() "de…